Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.11737 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913026246967296 |
|---|---|
| author | Stracke, Nick Bauer, Kolja Baumann, Stefan Andreas Bautista, Miguel Angel Susskind, Josh Ommer, Björn |
| author_facet | Stracke, Nick Bauer, Kolja Baumann, Stefan Andreas Bautista, Miguel Angel Susskind, Josh Ommer, Björn |
| contents | Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures through full video synthesis remains prohibitively inefficient. We model scene dynamics orders of magnitude more efficiently by directly operating on a long-term motion embedding that is learned from large-scale trajectories obtained from tracker models. This enables efficient generation of long, realistic motions that fulfill goals specified via text prompts or spatial pokes. To achieve this, we first learn a highly compressed motion embedding with a temporal compression factor of 64x. In this space, we train a conditional flow-matching model to generate motion latents conditioned on task descriptions. The resulting motion distributions outperform those of both state-of-the-art video models and specialized task-specific approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11737 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Long-term Motion Embeddings for Efficient Kinematics Generation Stracke, Nick Bauer, Kolja Baumann, Stefan Andreas Bautista, Miguel Angel Susskind, Josh Ommer, Björn Computer Vision and Pattern Recognition Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures through full video synthesis remains prohibitively inefficient. We model scene dynamics orders of magnitude more efficiently by directly operating on a long-term motion embedding that is learned from large-scale trajectories obtained from tracker models. This enables efficient generation of long, realistic motions that fulfill goals specified via text prompts or spatial pokes. To achieve this, we first learn a highly compressed motion embedding with a temporal compression factor of 64x. In this space, we train a conditional flow-matching model to generate motion latents conditioned on task descriptions. The resulting motion distributions outperform those of both state-of-the-art video models and specialized task-specific approaches. |
| title | Learning Long-term Motion Embeddings for Efficient Kinematics Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.11737 |